ModelPriceWatch.com
Last scan 2026-08-22 Models tracked 220 Providers 31 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

GPT-OSS 120B

by Groq · 120B parameters

Current fast open weights 500 TPS cheap tier

Today's price · per 1M tokens

Input

$0.150

per 1M tokens

Output

$0.600

per 1M tokens

Blended

$0.262

blended $/1M — 3:1 weighted input:output

Source: official Groq pricing · read Jul 4, 2026 MODELPRICEWATCH.COM · 2026-08-22

Price receipt

We read Groq's own pricing page on Aug 9, 2026 and found GPT OSS 120B listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 5268b840bd.

GPT-OSS 120B is available on 3 hosts. See the full cheapest-first comparison on the consolidated GPT-OSS 120B page →

Overview

OpenAI's open-source 120B model on Groq. ~500 tokens/sec. $0.15/$0.60 per 1M.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching Reasoning Coding Fast inference ✓ Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score65.5%
Perf per $/Mtok249.5
GPQA Diamond
80.1%
LiveCodeBench
69%
Humanity's Last Exam
14.9%
AIME 2025
97.9%
Independent composite scores
  • AA Intelligence Index: 24.1 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 13.4 (Tool use, planning, autonomy)
  • AA-Omniscience Index: -49.2 (−100–100)
How it stacks up
  • Ranks #41 of 69 benchmarked models by average score
  • Ranks #94 of 161 comparably-measured models by percentile score, across 7 independent measurements
  • Ranks #14 of 161 comparably-tested models by normalized performance per dollar
  • Strongest at AIME 2025 — 97.9%, #7 of 37

260 tokens/sec output

Source: Vellum LLM Leaderboard · updated Jun 29, 2026 · See full rankings →

Specifications

Provider
Groq
Context window
131K tokens
Modality
text
Parameters
120B
Open source
Yes — open weights available
Released
Jan 1, 2026
Status
Current
Last updated
Jul 4, 2026
Tags
fastopen-weightsspeed

Availability verified: Aug 9, 2026 — listed on Groq's own page